AI圈报
教程 / 实战普通

Flash-MoE: How to Run a 397B Model on a Laptop

信息来源：DEV Community·
Qwen

内容摘要

Flash-MoE streams a 397B Qwen model from SSD on a 48GB MacBook at 5.5 tok/s. No cloud. Here's how sparse MoE activation makes this actually work.
内容分类AI 教程与实战
内容层级普通情报
发布时间（北京时间）
本站收录时间（北京时间）
信息来源DEV Community
站内情报编号intel-48470e4def94b9e7e72ea923
阅读原始信息 ↗更多教程 / 实战

相关推荐

综合分类、实体标签与信息来源匹配

教程 / 实战普通
Qwen 3.6 Plus vs Claude Opus 4.6: Which One Actually Works in Production?
Qwen 3.6 Plus is free, fast, and ships 1M context. Claude Opus 4.6 costs more but handles hard agentic tasks better. Here's what actually matters.
信息来源：DEV Community · Qwen / Claude
教程 / 实战普通
I fine-tuned Qwen3-14B for my AI companion app for $1.30. The hard part wasn't the model
Soulor AI is an AI companion app with persistent memory and five relationship stages, from Stranger...
信息来源：DEV Community · Qwen
教程 / 实战普通
Export ChatGPT, Claude, Gemini, Grok, DeepSeek, Kimi, and Qwen chats to Markdown with Convolvger 0.6.0
If you have ever tried to export a ChatGPT conversation to Markdown, or save a Claude chat as a .md...
信息来源：DEV Community · ChatGPT / DeepSeek / Qwen
教程 / 实战普通
The provider that failed was the feature: building a model-agnostic AI arbiter (Kimi K2 · Qwen · EIP-712)
A real failure story from building EscrowLens, a passkey-native escrow protocol on Monad for the...
信息来源：DEV Community · Qwen / Kimi
教程 / 实战普通
Claude Code vs Qwen Code vs Codex
AI coding tools have changed. A couple of years ago, we were excited when autocomplete correctly...
信息来源：DEV Community · Qwen / Claude
教程 / 实战普通
Qwen3.8-27B: An Architecture and Hands-On Look at Alibaba's Compact Dense Model
In August 2026, less than a month after Moonshot AI's Kimi-K3 surprised the world, Alibaba Group...
信息来源：DEV Community · Qwen / Kimi
教程 / 实战普通
Hexagonal Architecture for Provider-Agnostic RAG Pipelines
Demo stack: LangChain, Llama.cpp, Mistral.ai, Qwen Embeddings, PostgreSQL, Telegraf, Prometheus on...
信息来源：DEV Community · Qwen / Llama / Mistral
教程 / 实战普通
I Rebuilt Jev's Structure with Qwen (Not Its Capabilities)
Jev does not generate an answer string. It makes a typed decision in one forward pass. So,...
信息来源：DEV Community · Qwen
教程 / 实战普通
Qianwen Office generates a multi-user app from a prompt. The prompt is the easy part.
On September 7, Alibaba's Qianwen Office (千问办公) launched a multi-person workspace. You describe who...
信息来源：DEV Community · Qwen
教程 / 实战普通
Best Local LLM for Coding: 8GB to 24GB VRAM Picks
The best local LLM for coding by VRAM bracket: Qwen3 Coder vs DeepSeek at 8, 12, 16 and 24 GB, the right quant per card, plus a runnable Ollama setup.
信息来源：DEV Community · DeepSeek / Qwen / Ollama